kvm: x86: Add exception payload fields to kvm_vcpu_events

The per-VM capability KVM_CAP_EXCEPTION_PAYLOAD (to be introduced in a
later commit) adds the following fields to struct kvm_vcpu_events:
exception_has_payload, exception_payload, and exception.pending.

With this capability set, all of the details of vcpu->arch.exception,
including the payload for a pending exception, are reported to
userspace in response to KVM_GET_VCPU_EVENTS.

With this capability clear, the original ABI is preserved, and the
exception.injected field is set for either pending or injected
exceptions.

When userspace calls KVM_SET_VCPU_EVENTS with
KVM_CAP_EXCEPTION_PAYLOAD clear, exception.injected is no longer
translated to exception.pending. KVM_SET_VCPU_EVENTS can now only
establish a pending exception when KVM_CAP_EXCEPTION_PAYLOAD is set.

Reported-by: Jim Mattson <jmattson@google.com>
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

3 files changed, 51 insertions, 18 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 20f7c994afeb..55e51ff7e421 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -919,6 +919,7 @@ struct kvm_arch {
 	bool x2apic_broadcast_quirk_disabled;
 
 	bool guest_can_read_msr_platform_info;
+	bool exception_payload_enabled;
 };
 
 struct kvm_vm_stat {
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index ab76aa1d3a4d..dabfcf7c3941 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -288,6 +288,7 @@ struct kvm_reinject_control {
 #define KVM_VCPUEVENT_VALID_SIPI_VECTOR	0x00000002
 #define KVM_VCPUEVENT_VALID_SHADOW	0x00000004
 #define KVM_VCPUEVENT_VALID_SMM		0x00000008
+#define KVM_VCPUEVENT_VALID_PAYLOAD	0x00000010
 
 /* Interrupt shadow states */
 #define KVM_X86_SHADOW_INT_MOV_SS	0x01
@@ -299,7 +300,7 @@ struct kvm_vcpu_events {
 		__u8 injected;
 		__u8 nr;
 		__u8 has_error_code;
-		__u8 pad;
+		__u8 pending;
 		__u32 error_code;
 	} exception;
 	struct {
@@ -322,7 +323,9 @@ struct kvm_vcpu_events {
 		__u8 smm_inside_nmi;
 		__u8 latched_init;
 	} smi;
-	__u32 reserved[9];
+	__u8 reserved[27];
+	__u8 exception_has_payload;
+	__u64 exception_payload;
 };
 
 /* for KVM_GET/SET_DEBUGREGS */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 532b660fe497..2ef706574589 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3373,19 +3373,33 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 					       struct kvm_vcpu_events *events)
 {
 	process_nmi(vcpu);
+
 	/*
-	 * FIXME: pass injected and pending separately.  This is only
-	 * needed for nested virtualization, whose state cannot be
-	 * migrated yet.  For now we can combine them.
+	 * The API doesn't provide the instruction length for software
+	 * exceptions, so don't report them. As long as the guest RIP
+	 * isn't advanced, we should expect to encounter the exception
+	 * again.
 	 */
-	events->exception.injected =
-		(vcpu->arch.exception.pending ||
-		 vcpu->arch.exception.injected) &&
-		!kvm_exception_is_soft(vcpu->arch.exception.nr);
+	if (kvm_exception_is_soft(vcpu->arch.exception.nr)) {
+		events->exception.injected = 0;
+		events->exception.pending = 0;
+	} else {
+		events->exception.injected = vcpu->arch.exception.injected;
+		events->exception.pending = vcpu->arch.exception.pending;
+		/*
+		 * For ABI compatibility, deliberately conflate
+		 * pending and injected exceptions when
+		 * KVM_CAP_EXCEPTION_PAYLOAD isn't enabled.
+		 */
+		if (!vcpu->kvm->arch.exception_payload_enabled)
+			events->exception.injected |=
+				vcpu->arch.exception.pending;
+	}
 	events->exception.nr = vcpu->arch.exception.nr;
 	events->exception.has_error_code = vcpu->arch.exception.has_error_code;
-	events->exception.pad = 0;
 	events->exception.error_code = vcpu->arch.exception.error_code;
+	events->exception_has_payload = vcpu->arch.exception.has_payload;
+	events->exception_payload = vcpu->arch.exception.payload;
 
 	events->interrupt.injected =
 		vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft;
@@ -3409,6 +3423,9 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 	events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
 			 | KVM_VCPUEVENT_VALID_SHADOW
 			 | KVM_VCPUEVENT_VALID_SMM);
+	if (vcpu->kvm->arch.exception_payload_enabled)
+		events->flags |= KVM_VCPUEVENT_VALID_PAYLOAD;
+
 	memset(&events->reserved, 0, sizeof(events->reserved));
 }
 
@@ -3420,12 +3437,24 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 	if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING
 			      | KVM_VCPUEVENT_VALID_SIPI_VECTOR
 			      | KVM_VCPUEVENT_VALID_SHADOW
-			      | KVM_VCPUEVENT_VALID_SMM))
+			      | KVM_VCPUEVENT_VALID_SMM
+			      | KVM_VCPUEVENT_VALID_PAYLOAD))
 		return -EINVAL;
 
-	if (events->exception.injected &&
-	    (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR ||
-	     is_guest_mode(vcpu)))
+	if (events->flags & KVM_VCPUEVENT_VALID_PAYLOAD) {
+		if (!vcpu->kvm->arch.exception_payload_enabled)
+			return -EINVAL;
+		if (events->exception.pending)
+			events->exception.injected = 0;
+		else
+			events->exception_has_payload = 0;
+	} else {
+		events->exception.pending = 0;
+		events->exception_has_payload = 0;
+	}
+
+	if ((events->exception.injected || events->exception.pending) &&
+	    (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR))
 		return -EINVAL;
 
 	/* INITs are latched while in SMM */
@@ -3435,13 +3464,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 
 	process_nmi(vcpu);
-	vcpu->arch.exception.injected = false;
-	vcpu->arch.exception.pending = events->exception.injected;
+	vcpu->arch.exception.injected = events->exception.injected;
+	vcpu->arch.exception.pending = events->exception.pending;
 	vcpu->arch.exception.nr = events->exception.nr;
 	vcpu->arch.exception.has_error_code = events->exception.has_error_code;
 	vcpu->arch.exception.error_code = events->exception.error_code;
-	vcpu->arch.exception.has_payload = false;
-	vcpu->arch.exception.payload = 0;
+	vcpu->arch.exception.has_payload = events->exception_has_payload;
+	vcpu->arch.exception.payload = events->exception_payload;
 
 	vcpu->arch.interrupt.injected = events->interrupt.injected;
 	vcpu->arch.interrupt.nr = events->interrupt.nr;